© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117498
    Prev
    Next
    INDEX
    Explanations

    "say" followed by declarative statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cendental
    -0.85
    usap
    -0.83
    ניס
    -0.81
    poop
    -0.80
     EPO
    -0.79
    paru
    -0.77
    ören
    -0.77
    reuters
    -0.77
     нещо
    -0.77
    یتی
    -0.76
    POSITIVE LOGITS
    дати
    0.83
     expre
    0.78
     airst
    0.75
    աշ
    0.71
    ange
    0.70
     gewesen
    0.69
    vieve
    0.68
     viszont
    0.67
    WISE
    0.67
     parrots
    0.66
    Activations Density 0.026%

    No Known Activations